Base44
Mini toolsLLaMA models
Browse all models from this model family.
to
-
Llama Guard 3 is Meta’s open-weight safety model for moderating AI prompts and responses. It classifies policy risks, returns structured JSON (allow/block with categories and rationale), and is designed to run beside your assistant for low-latency, context-aware guardrails.TextReleased 1y ago
-
Llama 3.2 Lightweight is Meta’s small-footprint Llama 3.2 line tuned for low-latency, low-cost deployment on a single GPU or edge device. It follows instructions well, writes code, supports tool/function calling and reliable JSON output, and ships as open weights under the Llama license.TextReleased 1y ago
-
Llama 3.3 70B is Meta’s updated 70B model in the Llama 3.x family, tuned for stronger reasoning, coding, and instruction following. It supports long-context prompting, tool/function calling, and reliable JSON outputs, with open weights under the Llama license.TextReleased 1y ago
-
Large Multimodal Model (Teacher); MoE architecture (16 experts, 288B active, ~2T total params); U...MultimodalReleased 10mo ago
-
Large Multimodal Model (Generalist); MoE architecture (128 experts, 17B active, 400B total params...TextReleased 10mo ago
-
Large Multimodal Model; MoE architecture (16 experts, 17B active, 109B total params), industry-le...TextReleased 10mo ago
-
Includes lightweight text models (1B, 3B for edge/mobile, 128k context) and vision models (11B, 9...TextReleased 1y ago
-
Meta's massive open-source LLM (405B parameters), rivaling top closed models and supporting fine-...TextReleased 1y ago
-
TextReleased 2y ago
-
LLaMA 2 Chat is Meta’s instruction tuned chat variant of LLaMA 2. It follows directions cleanly, handles multi turn dialogue, and provides safer, more helpful answers for everyday chat, drafting, and light coding.TextReleased 2y ago
-
LLaMA 2 is Meta’s second generation open-weight language model family. It ships in base and chat variants across multiple sizes, improves reasoning and coding over LLaMA, and is licensed for broad research and many commercial uses. It is a common starting point for fine-tuned assistants.TextReleased 2y ago
-
LLaMA is Meta’s foundation language model released for research. It offers strong zero and few shot ability at multiple sizes, runs efficiently compared with earlier large models, and became a common base for fine tuning and instruction tuned chat systems.TextReleased 3y ago
No models found
Try adjusting your search or filters.
